Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names containing "oh"

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.70
     Proced
    -0.68
     Panther
    -0.65
    ensional
    -0.63
     Falling
    -0.63
    ãĥ¯
    -0.61
     flush
    -0.61
    ãĥ¼ãĥĨãĤ£
    -0.61
     Instr
    -0.61
     pitted
    -0.60
    POSITIVE LOGITS
    awk
    1.15
    ansen
    1.00
    olics
    0.98
    ollow
    0.97
    awks
    0.95
    undred
    0.93
    oho
    0.93
    ometown
    0.89
    atche
    0.88
    ttp
    0.88
    Act Density 0.013%

    No Known Activations